ClawHub
Back to skill

Security audit

Generate Qrcode

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local QR-code generator that writes a PNG file to a user-chosen path.

Install only if you are comfortable with the skill creating directories and writing a PNG file wherever you direct it; choose an output path that will not replace an important existing file.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Session Persistence

Medium
Category
Rogue Agent
Content
## Usage

**IMPORTANT**: Use the existing Python script, don't write inline code.

```bash
python3 ~/.openclaw/skills/generate-qrcode/agent.py "<URL or text>" <output_path>
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Missing User Warnings

Low
Confidence
83% confidence
Finding
This is a markdown file, so SQP-2 applies to user-facing descriptions. The usage and examples show creation of a PNG at an output path, but there is no warning about filesystem effects such as creating or potentially overwriting a file, which could affect user data.

Static analysis

No suspicious patterns detected.